Mohamad Wahba
banner
m-wahba.bsky.social
Mohamad Wahba
@m-wahba.bsky.social
CS grad striving to master SWE & ML engineering 💻 | Passionate about Arabic NLP & advancing knowledge 🌍 | Exploring data, MLOps, math, science, and languages to build impactful solutions 🚀 | Lifelong learner 📚
Just enrolled in the 2025 𝐃𝐚𝐭𝐚 𝐄𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 𝐙𝐨𝐨𝐦𝐜𝐚𝐦𝐩 by DataTalksClub! 🚀

Can't wait to explore data engineering and grow with an amazing cohort. Big shoutout to DataTalksClub for this awesome opportunity!

#DataEngineering #LearningInPublic
January 14, 2025 at 3:12 AM
Reposted by Mohamad Wahba
For those who don’t feel like they fit into my Grumpy Machine Learners list (which I still need to update based on 100+ requests) I’ve created another starter pack:

go.bsky.app/Js7ka12

(Self) nominations welcome.
November 22, 2024 at 6:40 PM
Reposted by Mohamad Wahba
For those who wonder about the best way to start contributing to pytorch or open-source projects, here are the top three pointers I'd share:

1. The Ultimate Guide to PyTorch Contributions github.com/pytorch/pyto...
For pytorch core that should be the n1 item on your list.
The Ultimate Guide to PyTorch Contributions
Tensors and Dynamic neural networks in Python with strong GPU acceleration - pytorch/pytorch
github.com
November 23, 2024 at 2:13 PM
Reposted by Mohamad Wahba
Training variance is a thing and no one measures it because research models get trained once to beat the benchmark by 0.2 AP or whatever and then never trained again.

In prod one of the first things we do is train (the same model) a ton over different shuffled splits of the data in order to… 1/3
My issue with confidence intervals on datasets (often big enough sets that every change is sig) is that it only tests a set of parameters, whereas many papers make claims about a method/architecture/approach. If you only train one model your actual n=1.
November 22, 2024 at 10:00 PM
Reposted by Mohamad Wahba
You know the "🔹AI Overview" you get on Google Search?

I discovered today that it's repeating as fact something I made up 7 years ago as a joke.

"Kyloren syndrome" is a fictional disease I invented as part of a sting operation to prove that you can publish any nonsense in predatory journals...
November 22, 2024 at 4:06 PM
Reposted by Mohamad Wahba
Here's a walk-through of a general-purpose approach to solving many types of optimization problem. It's often not the most efficient way, but it is often fast enough, and it doesn't require using different methods for different problems.
youtu.be/U2b5Cacertc
Using Excel for optimization problems
YouTube video by Jeremy Howard
youtu.be
November 19, 2024 at 11:17 PM
Reposted by Mohamad Wahba
Just realized BlueSky allows sharing valuable stuff cause it doesn't punish links. 🤩

Let's start with "What are embeddings" by @vickiboykis.com

The book is a great summary of embeddings, from history to modern approaches.

The best part: it's free.

Link: vickiboykis.com/what_are_emb...
November 22, 2024 at 11:13 AM